小红书技术产品-算法平台
社招全职3-5年产品经理地点:北京 | 上海状态:招聘
任职要求
我们希望你
· 计算机/软件/数据相关本科及以上,具备数据或机器学习平台产品经验
· 深刻理解特征全生命周期与关键难题:点时拼接、反泄露、回填、训练-服务一致性、版本化与回滚
· 对批流计算与数据存储有体系化认知:Spark/Flink、Kafka;数据湖/仓(Hudi/Iceberg/Delta);OLAP 与 KV/列存(HBase/Cassandra/Redis/DynamoDB 等)
· 熟悉在线推理链路与A/B实验,能将SLO/成本/稳定性约束转化为可落地的产品与技术方案
· 逻辑严,抽象佳,敢创新,落地快,owner 意识,学习能力强…登录查看完整任职要求
微信扫码,1秒登录
工作职责
公司级产品
· 搭建小红书统一的特征平台(AI-Drive),贯通特征从采集、开发、回填、验证、上线到监控的全生命周期,支撑推荐/广告/搜索等核心业
· 确保训练-服务一致性,提升特征复用率,降低新特征从想法到上线的时间与成本
你将负责
· 制定产品愿景与路线图:明确平台边界、阶段目标与成功指标
· 需求洞察与优先级:深入算法、数据、工程、业务团队,沉淀标准化用户旅程与规范(特征定义、开发、点时拼接、回填、上线、治理)
· 核心能力涉及:
· 特征注册/目录/发现(Feature Registry & Catalog)、元数据与版本化、血缘与审计
· 批流一体计算与物化(Spark/Flink + Kafka/Pulsar;离线/准实时/实时)
· 点时间隔离与防数据泄露(point-in-time join, leakage prevention)
· 训练-服务一致性与回放校验,A/B 切换与特征开关
· 在线特征存储与缓存(低延迟、高可用、冷热层次),多租户与限流
· 数据质量与监控(Schema 变更、漂移检测、告警自愈)
· 成本与容量治理(计算/存储成本、QPS/吞吐/延迟SLO)
· 交付与落地:
· 撰写PRD/原型/时序图,拆解里程碑,推动研发、测试、灰度、可观测性、运维准备到位
· 建设文档、模板、示例库与工作坊,推动平台采用与特征复用
· 生态集成:对接数据湖/仓(Hudi/Iceberg/Delta、Hive/Trino/Presto)、特征/模型平台(Feast、Kubeflow/Airflow、MLflow/KServe)、监控/数据治理(DataHub/Amundsen、OpenLineage、Great Expectations/Deequ)
我们提供
· 有行业影响力的挑战与规模化应用场景
· 以人为本,开放的工程文化与跨团队协作氛围包括英文材料
学历+
AI agent+
https://www.ibm.com/think/ai-agents
Your one-stop resource for gaining in-depth knowledge and hands-on applications of AI agents.
DevOps+
https://roadmap.sh/devops
Step by step guide for DevOps, SRE or any other Operations Role in 2025
https://zhuanlan.zhihu.com/p/562036793
DevOps中的Dev指的是Development(开发),Ops指的是Operations(运维),用一句话来说,DevOps就是打通开发运维的壁垒,实现开发运维一体化。
Python+
https://liaoxuefeng.com/books/python/introduction/index.html
中文,免费,零起点,完整示例,基于最新的Python 3版本。
https://www.learnpython.org/
a free interactive Python tutorial for people who want to learn Python, fast.
https://www.youtube.com/watch?v=K5KVEU3aaeQ
Master Python from scratch 🚀 No fluff—just clear, practical coding skills to kickstart your journey!
https://www.youtube.com/watch?v=rfscVS0vtbw
This course will give you a full introduction into all of the core concepts in python.
Java+
https://www.youtube.com/watch?v=eIrMbAQSU34
Master Java – a must-have language for software development, Android apps, and more! ☕️ This beginner-friendly course takes you from basics to real coding skills.
算法+
https://roadmap.sh/datastructures-and-algorithms
Step by step guide to learn Data Structures and Algorithms in 2025
https://www.hellointerview.com/learn/code
A visual guide to the most important patterns and approaches for the coding interview.
https://www.w3schools.com/dsa/
机器学习+
https://www.youtube.com/watch?v=0oyDqO8PjIg
Learn about machine learning and AI with this comprehensive 11-hour course from @LunarTech_ai.
https://www.youtube.com/watch?v=i_LwzRVP7bg
Learn Machine Learning in a way that is accessible to absolute beginners.
https://www.youtube.com/watch?v=NWONeJKn6kc
Learn the theory and practical application of machine learning concepts in this comprehensive course for beginners.
https://www.youtube.com/watch?v=PcbuKRNtCUc
Learn about all the most important concepts and terms related to machine learning and AI.
Spark+
[英文] Learning Spark Book
https://pages.databricks.com/rs/094-YMS-629/images/LearningSpark2.0.pdf
This new edition has been updated to reflect Apache Spark’s evolution through Spark 2.x and Spark 3.0, including its expanded ecosystem of built-in and external data sources, machine learning, and streaming technologies with which Spark is tightly integrated.
Flink+
https://nightlies.apache.org/flink/flink-docs-release-2.0/docs/learn-flink/overview/
This training presents an introduction to Apache Flink that includes just enough to get you started writing scalable streaming ETL, analytics, and event-driven applications, while leaving out a lot of (ultimately important) details.
https://www.youtube.com/watch?v=WajYe9iA2Uk&list=PLa7VYi0yPIH2GTo3vRtX8w9tgNTTyYSux
Today’s businesses are increasingly software-defined, and their business processes are being automated. Whether it’s orders and shipments, or downloads and clicks, business events can always be streamed. Flink can be used to manipulate, process, and react to these streaming events as they occur.
Kafka+
https://developer.confluent.io/what-is-apache-kafka/
https://www.youtube.com/watch?v=CU44hKLMg7k
https://www.youtube.com/watch?v=j4bqyAMMb7o&list=PLa7VYi0yPIH0KbnJQcMv5N9iW8HkZHztH
In this Apache Kafka fundamentals course, we introduce you to the basic Apache Kafka elements and APIs, as well as the broader Kafka ecosystem.
Hudi+
[英文] Spark Quick Start
https://hudi.apache.org/docs/quick-start-guide
we will walk through code snippets that allows you to insert, update, delete and query a Hudi table.
https://www.oreilly.com/library/view/apache-hudi-the/9781098173821/
Overcome challenges in building transactional guarantees on rapidly changing data by using Apache Hudi.
https://www.youtube.com/watch?v=pyK18sDYnS0
In this video, I'll introduce you to one of the most popular Data Lake solutions out there, Apache Hudi!
还有更多 •••
相关职位
社招TEG产品
1.深入理解具身智能开放平台算法模型以及提供的技术服务,面向机器人行业开发者推广并跟进开发者使用效果;组织面向开发者的各类活动,提升平台用户覆盖和活跃; 2.面向具身智能领域开发者群体运营,针对开发者关于具身智能相关算法、数据集、仿真环境等相关技术问题提供技术支持,维护开发者关系; 3.与研发团队保持紧密协作,及时传递市场需求与客户反馈,驱动产品持续迭代与优化。
更新于 2025-05-29深圳

社招技术支持序列
1、面向客户,配合项目经理及产品经理,基于地平线征程计算平台+算法工具链+参考算法进行产品技术方案宣讲; 2、独立管理和把控客户工具链+算法解决方案的 Design IN 全流程,提供技术方案、问题分析等各种技术支持;积极推动客户项目量产落地,最终促进公司商业目标达成; 3、跟踪业界领先自动驾驶算法、大模型(LLM/VLM/VLA)算法,深度理解地平线征程计算平台的优势算法模型结构,推动最优的解决方案在行业中落地; 4、挖掘和掌握客户需求,了解行业竞品发展趋势,参与地平线征程计算平台+算法工具链+大模型部署相关内部产品定义、设计、开发与评测等。
更新于 2025-07-23南京